Agent Systems

Tree-Structured Trajectory Encoding for Vision-and-Language Navigation AAAI 2023 Triplet-Free Knowledge-Guided Response Generation ACL 2023 Tuning Legged Locomotion Controllers via Safe Bayesian Optimization CoRL 2023 UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding CoRL 2023 Uniformly Conservative Exploration in Reinforcement Learning AISTATS 2023 Universal Agent Mixtures and the Geometry of Intelligence AISTATS 2023 Unsupervised Skill Discovery for Learning Shared Structures across Changing Environments ICML 2023 Using Learning Analytics for Adaptive Exercise Generation ACL 2023 VERVE: Template-based ReflectiVE Rewriting for MotiVational IntErviewing EMNLP 2023 Vision Language Navigation with Knowledge-driven Environmental Dreamer IJCAI 2023 VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models CoRL 2023 Warm-Starting Nested Rollout Policy Adaptation with Optimal Stopping AAAI 2023 Waverunner: An Elegant Approach to Hardware Acceleration of State Machine Replication NSDI 2023 We Are What We Repeatedly Do: Inducing and Deploying Habitual Schemas in Persona-Based Responses EMNLP 2023 What Planning Problems Can A Relational Neural Network Solve? NeurIPS 2023 What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery CoRL 2023 Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive Teachers ACL 2023 Zero-Shot Assistance in Sequential Decision Problems AAAI 2023 A Closed-Loop Perception, Decision-Making and Reasoning Mechanism for Human-Like Navigation IJCAI 2022 Action-modulated midbrain dopamine activity arises from distributed control policies NeurIPS 2022 Active Hierarchical Exploration with Stable Subgoal Representation Learning ICLR 2022 Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game ICLR 2022 ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments COLING 2022 Adaptive Model Design for Markov Decision Process ICML 2022 ADAPT: Vision-Language Navigation With Modality-Aligned Action Prompts CVPR 2022